Imperial College London
Alternate

Professor Anil Anthony Bharath

Faculty of Engineering, Department of Bioengineering

Academic Director (Singapore)
 
 
 
//

Contact

 

+44 (0)20 7594 5463a.bharath Website

 
 
//

Location

 

4.12Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Creswell:2016:10.1007/978-3-319-46604-0_55,
author = {Creswell, A and Bharath, AA},
doi = {10.1007/978-3-319-46604-0_55},
publisher = {Springer Verlag},
title = {Adversarial training for sketch retrieval},
url = {http://dx.doi.org/10.1007/978-3-319-46604-0_55},
year = {2016}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Generative Adversarial Networks (GAN) are able to learn excellentrepresentations for unlabelled data which can be applied to image generationand scene classification. Representations learned by GANs have not yet beenapplied to retrieval. In this paper, we show that the representations learnedby GANs can indeed be used for retrieval. We consider heritage documents thatcontain unlabelled Merchant Marks, sketch-like symbols that are similar tohieroglyphs. We introduce a novel GAN architecture with design features thatmake it suitable for sketch retrieval. The performance of this sketch-GAN iscompared to a modified version of the original GAN architecture with respect tosimple invariance properties. Experiments suggest that sketch-GANs learnrepresentations that are suitable for retrieval and which also have increasedstability to rotation, scale and translation compared to the standard GANarchitecture.
AU  - Creswell,A
AU  - Bharath,AA
DO  - 10.1007/978-3-319-46604-0_55
PB  - Springer Verlag
PY  - 2016///
SN  - 0302-9743
TI  - Adversarial training for sketch retrieval
UR  - http://dx.doi.org/10.1007/978-3-319-46604-0_55
UR  - http://arxiv.org/abs/1607.02748v2
UR  - http://hdl.handle.net/10044/1/53492
ER  -
Download